Clinically, non-contrastive computed tomography (NCCT) is used to quickly diagnose the type and area of stroke, and the Alberta stroke program early computer tomography score (ASPECTS) is used to guide the next treatment. However, in the early stage of acute ischemic stroke (AIS), it’s difficult to distinguish the mild cerebral infarction on NCCT with the naked eye, and there is no obvious boundary between brain regions, which makes clinical ASPECTS difficult to conduct. The method based on machine learning and deep learning can help physicians quickly and accurately identify cerebral infarction areas, segment brain areas, and operate ASPECTS quantitative scoring, which is of great significance for improving the inconsistency in clinical ASPECTS. This article describes current challenges in the field of AIS ASPECTS, and then summarizes the application of computer-aided technology in ASPECTS from two aspects including machine learning and deep learning. Finally, this article summarizes and prospects the research direction of AIS-assisted assessment, and proposes that the computer-aided system based on multi-modal images is of great value to improve the comprehensiveness and accuracy of AIS assessment, which has the potential to open up a new research field for AIS-assisted assessment.
ObjectiveTo compare the application effects between personal specific instrumentation (PSI) and computer-assisted navigation surgery (CAS) in total knee arthroplasty (TKA). MethodsThe literature comparing the application effects of PSI and CAS in TKA in recent years was widely consulted, and the difference between PSI-TKA and CAS-TKA in operation time, lower limb alignment, blood loss, and knee function were compared. ResultsCompared to CAS-TKA, PSI-TKA simplifies operation procedures and shortens operation time but probably has worse lower limb alignment. It is still controversial in comparison of perioperative blood loss and knee function between two techniques. ConclusionPSI-TKA and CAS-TKA both have advantages and disadvantages, and their differences need to be confirmed by further high-quality clinical trial.
Objective To improve the accuracy of the acetabular component placement using the nonimage based surgical navigation system. Methods Twenty-three patients (14 males, 9 females; age, 28-55 years;26 hips）with hip disease underwent the total hip arthroplasty (THA) using the nonimage based surgicalnavigation system from February 2004 to April 2006. Rheumatoid arthritis was found in 3 patients (3 hips), necrosis of the femoral head in 6 patients (6 hips), and osteoarthritis in 14 patients (16 hips). All the patients were randomly divided into the following 2 groups: the navigated group (11 patients, 13 hips), treated by THA using the nonimage based surgical navigation system; and the control group (12 patients, 13 hips), treated by the traditional THA. According to thedesign of the study, the acetabular component was placed in the best inclination angle (45°) and the anteversion angle (15°). The postoperative component position was examined. Results No fracture, dislocation, infection or injury to the sciatic nerve was found. In the navigated group, the inclination and the anteversion reached 15.4±1.4° and 45.5±1.3°, respectively. In the control group,the inclination and the anteversion were 13.9±7.6° and 43.7±6.4°, respectively. The inclination difference was considered statistically significant (Plt;0.01). All the patients were followed up for 10-40 months,averaged 26 months. In the navigated group, the postoperative average Harris hip score was 95 (range,85-110), with an excellent result in 11 hips and a good result in 2 hips. In the control group, the postoperative average Harris hip score was 92 (range,75-110), with an excellent result in 9 hips, a good result in 3 hips, and a fair result in 1 hip. The Harris hip score difference was considered statistically significant (Plt;0.05). There was a significantly better result obtained in the navigated group than in the control group. Conclusion The acetabular component can be implanted accurately by the nonimage based surgical navigation system, which can reduce the incidence of the loosening of the prostheses and has an important value in clinical practice.
At present, artificial intelligence (AI) has been widely used in the diagnosis and treatment of various ophthalmological diseases, but there are still many problems. Due to the lack of standardized test sets, gold standards, and recognized evaluation systems for the accuracy of AI products, it is difficult to compare the results of multiple studies. When it comes to the field of image generation, we hardly have an efficient approach to evaluating research results. In clinical practice, ophthalmological AI research is often out of touch with actual clinical needs. The requirements for the quality and quantity of clinical data put more burden on AI research, limiting the transformation of AI studies. The prediction of systemic diseases based on fundus images is making progressive advancement. However, the lack of interpretability of the research lower the acceptance. Ophthalmology AI research also suffer from ethical controversy due to unconstructed regulations and regulatory mechanisms, concerns on patients’ privacy and data security, and the risk of aggravating the unfairness of medical resources.
Objective To observe the characteristics of morphological development of premature retina at 33-46 weeks of gestational corrected age (GCA). Methods A total of 268 premature infants were divided into 7 groups according to the GCA (33-34，35-36，37-38，39-40，41-42，43-44 and 45-46 weeks). The ocular fundus of those infants were recorded and analyzed by an indirect ophthalmoscopelinked imaging system. Results As GCA increases, noticeable macular morphological changes occurred and recorded in 96% of infant at 45-46 weeks of GCA. Retinas were gradually vascularized at 41-42 weeks (nasal retina) or 43-44 weeks (area Ⅲ,temporal retina), and pigmented in 84% of infant at 45-46 weeks of GCA. Conclusion Macular morphological patterns, retinal blood vessels and pigments continue to develop in postnatal premature infants.
Objective To summarize the research progress of the causes and prevention methods of anterior femoral notching in total knee arthroplasty (TKA). Methods The related literature at home and abroad about the causes and prevention methods of the anterior femoral notching in TKA was extensively reviewed and summarized. Results The reasons for the occurrence of anterior femoral notching can be summarized as follows: the application of the posterior reference technique, the increase of the posterior condylar angle, the variant anatomical shape of anterior femoral cortex, the selective reduction of the femoral prosthesis size, backward movement of the entrance point, and the application of computer-assisted navigation technology or patient-specific instrumentation. To prevent the occurrence of anterior femoral notching, programs such as flex the femoral prosthesis, robot-assisted technology, and anterior and posterior reference techniques combination can be used. Conclusion Anterior femoral notching is a common surgical complication of TKA. A complete preoperative plan, assessment of the patient’s knee joint condition, and development of a reasonable surgical plan can effectively reduce the occurrence of anterior femoral notching.
ObjectiveTo investigate the application and technical essentials of computer-assisted navigation in the surgical management of periacetabular fractures and pelvic fractures. MethodsBetween May 2010 and May 2011, 39 patients with periacetabular or anterior and posterior pelvic ring fractures were treated by minimally invasive fixation under computer-assisted navigation and were followed up more than 2 years, and the clinical data were analyzed retrospectively. There were 21 males and 18 females, aged 15-64 years (mean, 36 years). Fractures were caused by traffic accident in 23 cases, crush injury in 6 cases, and falling from height in 10 cases. Of them, 6 cases had acetabular fractures; 6 cases had femoral neck fractures; 18 cases had dislocation of sacroiliac joint; and 15 cases had anterior pelvic ring injuries. All patients were treated with closed or limited open reduction and screw fixations assisted with navigation. ResultsEighty-nine screws were inserted during operation, including 8 in the acetabulum, 18 in the neck of the femur, 33 in the sacroiliac joint, and 30 in the symphysis pubis and pubic rami. The mean time of screw implanted was 20 minutes (range, 11-38 minutes), and the average blood loss volume was 20 mL (range, 10-50 mL). The postoperative pelvic X-ray and three dimensional CT scan showed good reduction of fractures and good position of the screws. No incision infection, neurovascular injury, or implant failure occurred. All patients were followed up 27-33 months with an average of 29.6 months. The patients could walk with full weight loading at 6-12 weeks after operation (mean, 8 weeks); at last follow-up, the patients could walk on the flat ground, stand with one leg, and squat down, and they recovered well enough to do their job and to live a normal life. ConclusionMinimally invasive fixation under computer-assisted navigation may be an excellent method to treat some specific types of periacetabular and anterior and posterior pelvic ring fractures because it has the advantages of less trauma and blood loss, lower complication incidence, and faster recovery.
Lung cancer has brought tough challenges to human health due to its high incidence and mortality rate in the current practice. Nowadays, computed tomography (CT) imaging is still the most preferred diagnostic tool for early screening of lung cancer. However, a great challenge brought from accumulative CT imaging data can not meet the demand of the current clinical practice. As a novel kind of artificial intelligence technique aimed to deal with medical images, a computer-aided diagnosis has been found to provide useful auxiliary information, attenuate the workload of doctors, and significantly improve the efficiency and accuracy for clinical diagnosis of lung cancer. Therefore, an effective combination of computer-aided techniques and CT imaging has increasingly become an active area of investigation in early diagnosis of lung cancer. This review aims to summarize the latest progress on the diagnostic value of computer-aided technology with regard to early stage lung cancer from the perspectives of machine learning and deep learning.
Objective To investigate effectiveness of applying the Bone Morphingbased image-free computer-assisted system for the ligament balancing managementin the total knee arthroplasty (TKA). Methods Between November 2002 and June 2003, twenty-one posterior stabilized total knee prostheses (Ceraver, France) were implanted in 21 patients using the Bone Morphing based image-free Ceravision system.This cohort included 5 men and 16 women with an average age of 72.4 years, two undergoing high tibial osteotomy and 1 undergoing distal femoral osteotomy before. The preoperative deviation was measured by the full-length AP X-rays. The knees were in varus deviation in 14 patients and in valgus deviation in 7 patients, with an average of 2.36°(varus 13°-valgus 13°). The frontal X-rays ofthe knee were assessed, the mean value of the varus force-stress test was 8.47°(varus 2°-varus 20°), and the mean value of the valgus forcestress test was 3.63°(varus 7°-valgus 12°). Results With the Ceravisionrecorded data, the intraoperative alignment was assessed, the mean lower limb axis was 3.33°(varus 12°-valgus 10°),and compared with the preoperative data, the difference was significant (Plt;0.05); the mean value of the varus force-stress test was 6.47°(varus 0°-varus 24°), the mean value of the valgus force-stress test was 4.32°(varus 8°- valgus 15°), and compared with the preoperative data, the difference was significant (Plt;0.05). The post-prosthetic alignment on Ceravision with a deviation of 0.175°(varus 2°- valgus 3°) was compared with the postoperative alignment by the full-length AP X-rays, with a deviation of 0.3°(varus 3.5°-valgus 1.5°), the difference wasn’t significant(Pgt;0.05).The clinical check-up performed 3 months after operation showed that the average range of movement (ROM) was 115°(105-130°), the mean frontal laxity was 0.27 mm(0.2-0.5 mm). The femoral and tibial components were implanted in the satisfactory 3 dimensional position without ligament imbalance in all the patients, andthere were no instability or patella complications.Conclusion Utilization of the Bone Morphing based image-free computer-assisted system can achieve an accurate component 3 dimensional alignment, optimal bone resection, optimal control of surgical decision in releasing the soft tissues, rotating the femoral component to gain an extension/flexion rectangular gap, and managing theligament balancing so as to achieve a satisfactory initial clinical outcome. This system can be routinely used in the TKA.
Objective To explore the therapeutic effect of rehabilitation therapy combined with computer-aided design and computer-aided manufacture (CAD/CAM) of orthopedic insoles on deputy scaphoid inflammation. Methods We selected the patients with deputy scaphoid inflammation who had treated in Sichuan Province Orthopedic Hospital between July 2018 and February 2020. The patients were randomly divided into control group and experimental group by drawing lots. The control group received rehabilitation therapy, while the experimental group received rehabilitation therapy combined with CAD/CAM orthopedic insoles. The clinical efficacy was tested at the 5th and 12th weeks after treatment, and the foot pain was assessed by Visual Analogue Scoring (VAS), and the foot function was assessed by the American Orthopaedic Foot and Ankle Association (AOFAS) scale. Results A total of 78 patients were included, and 3 patients dropped out. There was no significant difference in sex, age, weight or course of disease between the two groups (P>0.05). Before treatment, there was no statistically significant difference in VAS score (t=0.329, P=0.743) or AOFAS score (t=0.431, P=0.668) between the two groups. At the 5th and 12th weeks after treatment, the VAS score of the experimental group was lower than that of the control group (t=4.517, 5.299; P<0.001), and the AOFAS score was higher than that of the control group (t=6.239, 5.779; P<0.001). Over time, the VAS score of the two groups decreased (P<0.05), while the AOFAS score increased (P<0.05). Conclusion Rehabilitation therapy combined with CAD/CAM of orthopedic insoles have better curative effect than traditional rehabilitation therapy for deputy scaphoid inflammation.